提出正交低秩变换，稳定推荐系统嵌入空间。
Orthogonal Low Rank Embedding Stabilization
- 用低秩SVD与正交Procrustes变换对齐嵌入空间。
- 实现无损映射，保持点积与推理质量不变。
- 轻量高效，可无缝集成到现有系统中。
模型重训练时嵌入空间的不稳定性给下游应用带来挑战，尤其当推荐系统生成的用户或物品嵌入作为特征输入时。本文提出一种新颖的正交低秩变换方法，旨在稳定用户/物品嵌入空间，确保重训练周期间嵌入维度一致。该方法结合高效的低秩奇异值分解与正交Procrustes变换，将嵌入映射至标准化空间。该变换计算高效、无损且轻量，保留点积关系与推理质量，同时降低运维负担。与修改训练目标或嵌入结构的现有方法不同，本方法保持主模型完整，可无缝衔接其他稳定化技术。
原文摘要 · Abstract (English)
The instability of embedding spaces across model retraining cycles presents significant challenges to downstream applications using user or item embeddings derived from recommendation systems as input features. This paper introduces a novel orthogonal low-rank transformation methodology designed to stabilize the user/item embedding space, ensuring consistent embedding dimensions across retraining sessions. Our approach leverages a combination of efficient low-rank singular value decomposition and orthogonal Procrustes transformation to map embeddings into a standardized space. This transformation is computationally efficient, lossless, and lightweight, preserving the dot product and inference quality while reducing operational burdens. Unlike existing methods that modify training objectives or embedding structures, our approach maintains the integrity of the primary model application and can be seamlessly integrated with other stabilization techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。